RL · Reinforcement Learning
Training that optimizes a model against a reward signal rather than labeled data; post-training RL mixes training and inference and loads clusters in spiky patterns.
Current numbers
~24K tokensMean trajectory length in AgentMath's reported agentic-RL analysis
2.5xWall-clock speedup of variance-controlled async RL over synchronous at equal accuracy (~42h vs ~105h)